@mariozechner/pi-ai 0.5.45 → 0.5.47

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -2,6 +2,23 @@
2
2
  // Do not edit manually - run 'npm run generate-models' to update
3
3
  export const MODELS = {
4
4
  anthropic: {
5
+ "claude-opus-4-0": {
6
+ id: "claude-opus-4-0",
7
+ name: "Claude Opus 4 (latest)",
8
+ api: "anthropic-messages",
9
+ provider: "anthropic",
10
+ baseUrl: "https://api.anthropic.com",
11
+ reasoning: true,
12
+ input: ["text", "image"],
13
+ cost: {
14
+ input: 15,
15
+ output: 75,
16
+ cacheRead: 1.5,
17
+ cacheWrite: 18.75,
18
+ },
19
+ contextWindow: 200000,
20
+ maxTokens: 32000,
21
+ },
5
22
  "claude-3-5-sonnet-20241022": {
6
23
  id: "claude-3-5-sonnet-20241022",
7
24
  name: "Claude Sonnet 3.5 v2",
@@ -19,6 +36,40 @@ export const MODELS = {
19
36
  contextWindow: 200000,
20
37
  maxTokens: 8192,
21
38
  },
39
+ "claude-opus-4-1": {
40
+ id: "claude-opus-4-1",
41
+ name: "Claude Opus 4.1 (latest)",
42
+ api: "anthropic-messages",
43
+ provider: "anthropic",
44
+ baseUrl: "https://api.anthropic.com",
45
+ reasoning: true,
46
+ input: ["text", "image"],
47
+ cost: {
48
+ input: 15,
49
+ output: 75,
50
+ cacheRead: 1.5,
51
+ cacheWrite: 18.75,
52
+ },
53
+ contextWindow: 200000,
54
+ maxTokens: 32000,
55
+ },
56
+ "claude-haiku-4-5": {
57
+ id: "claude-haiku-4-5",
58
+ name: "Claude Haiku 4.5 (latest)",
59
+ api: "anthropic-messages",
60
+ provider: "anthropic",
61
+ baseUrl: "https://api.anthropic.com",
62
+ reasoning: true,
63
+ input: ["text", "image"],
64
+ cost: {
65
+ input: 1,
66
+ output: 5,
67
+ cacheRead: 0.1,
68
+ cacheWrite: 1.25,
69
+ },
70
+ contextWindow: 200000,
71
+ maxTokens: 64000,
72
+ },
22
73
  "claude-3-5-sonnet-20240620": {
23
74
  id: "claude-3-5-sonnet-20240620",
24
75
  name: "Claude Sonnet 3.5",
@@ -36,6 +87,23 @@ export const MODELS = {
36
87
  contextWindow: 200000,
37
88
  maxTokens: 8192,
38
89
  },
90
+ "claude-3-5-haiku-latest": {
91
+ id: "claude-3-5-haiku-latest",
92
+ name: "Claude Haiku 3.5 (latest)",
93
+ api: "anthropic-messages",
94
+ provider: "anthropic",
95
+ baseUrl: "https://api.anthropic.com",
96
+ reasoning: false,
97
+ input: ["text", "image"],
98
+ cost: {
99
+ input: 0.8,
100
+ output: 4,
101
+ cacheRead: 0.08,
102
+ cacheWrite: 1,
103
+ },
104
+ contextWindow: 200000,
105
+ maxTokens: 8192,
106
+ },
39
107
  "claude-3-opus-20240229": {
40
108
  id: "claude-3-opus-20240229",
41
109
  name: "Claude Opus 3",
@@ -53,6 +121,23 @@ export const MODELS = {
53
121
  contextWindow: 200000,
54
122
  maxTokens: 4096,
55
123
  },
124
+ "claude-sonnet-4-5": {
125
+ id: "claude-sonnet-4-5",
126
+ name: "Claude Sonnet 4.5 (latest)",
127
+ api: "anthropic-messages",
128
+ provider: "anthropic",
129
+ baseUrl: "https://api.anthropic.com",
130
+ reasoning: true,
131
+ input: ["text", "image"],
132
+ cost: {
133
+ input: 3,
134
+ output: 15,
135
+ cacheRead: 0.3,
136
+ cacheWrite: 3.75,
137
+ },
138
+ contextWindow: 200000,
139
+ maxTokens: 64000,
140
+ },
56
141
  "claude-sonnet-4-5-20250929": {
57
142
  id: "claude-sonnet-4-5-20250929",
58
143
  name: "Claude Sonnet 4.5",
@@ -155,60 +240,26 @@ export const MODELS = {
155
240
  contextWindow: 200000,
156
241
  maxTokens: 64000,
157
242
  },
158
- "claude-opus-4-1-20250805": {
159
- id: "claude-opus-4-1-20250805",
160
- name: "Claude Opus 4.1",
243
+ "claude-3-7-sonnet-latest": {
244
+ id: "claude-3-7-sonnet-latest",
245
+ name: "Claude Sonnet 3.7 (latest)",
161
246
  api: "anthropic-messages",
162
247
  provider: "anthropic",
163
248
  baseUrl: "https://api.anthropic.com",
164
249
  reasoning: true,
165
250
  input: ["text", "image"],
166
- cost: {
167
- input: 15,
168
- output: 75,
169
- cacheRead: 1.5,
170
- cacheWrite: 18.75,
171
- },
172
- contextWindow: 200000,
173
- maxTokens: 32000,
174
- },
175
- "claude-3-sonnet-20240229": {
176
- id: "claude-3-sonnet-20240229",
177
- name: "Claude Sonnet 3",
178
- api: "anthropic-messages",
179
- provider: "anthropic",
180
- baseUrl: "https://api.anthropic.com",
181
- reasoning: false,
182
- input: ["text", "image"],
183
251
  cost: {
184
252
  input: 3,
185
253
  output: 15,
186
254
  cacheRead: 0.3,
187
- cacheWrite: 0.3,
188
- },
189
- contextWindow: 200000,
190
- maxTokens: 4096,
191
- },
192
- "claude-haiku-4-5-20251001": {
193
- id: "claude-haiku-4-5-20251001",
194
- name: "Claude Haiku 4.5",
195
- api: "anthropic-messages",
196
- provider: "anthropic",
197
- baseUrl: "https://api.anthropic.com",
198
- reasoning: true,
199
- input: ["text", "image"],
200
- cost: {
201
- input: 1,
202
- output: 5,
203
- cacheRead: 0.1,
204
- cacheWrite: 1.25,
255
+ cacheWrite: 3.75,
205
256
  },
206
257
  contextWindow: 200000,
207
258
  maxTokens: 64000,
208
259
  },
209
260
  "claude-sonnet-4-0": {
210
261
  id: "claude-sonnet-4-0",
211
- name: "Claude Sonnet 4",
262
+ name: "Claude Sonnet 4 (latest)",
212
263
  api: "anthropic-messages",
213
264
  provider: "anthropic",
214
265
  baseUrl: "https://api.anthropic.com",
@@ -223,59 +274,42 @@ export const MODELS = {
223
274
  contextWindow: 200000,
224
275
  maxTokens: 64000,
225
276
  },
226
- "claude-3-7-sonnet-latest": {
227
- id: "claude-3-7-sonnet-latest",
228
- name: "Claude Sonnet 3.7",
277
+ "claude-opus-4-1-20250805": {
278
+ id: "claude-opus-4-1-20250805",
279
+ name: "Claude Opus 4.1",
229
280
  api: "anthropic-messages",
230
281
  provider: "anthropic",
231
282
  baseUrl: "https://api.anthropic.com",
232
283
  reasoning: true,
233
284
  input: ["text", "image"],
234
285
  cost: {
235
- input: 3,
236
- output: 15,
237
- cacheRead: 0.3,
238
- cacheWrite: 3.75,
286
+ input: 15,
287
+ output: 75,
288
+ cacheRead: 1.5,
289
+ cacheWrite: 18.75,
239
290
  },
240
291
  contextWindow: 200000,
241
- maxTokens: 64000,
292
+ maxTokens: 32000,
242
293
  },
243
- "claude-sonnet-4-5": {
244
- id: "claude-sonnet-4-5",
245
- name: "Claude Sonnet 4.5",
294
+ "claude-3-sonnet-20240229": {
295
+ id: "claude-3-sonnet-20240229",
296
+ name: "Claude Sonnet 3",
246
297
  api: "anthropic-messages",
247
298
  provider: "anthropic",
248
299
  baseUrl: "https://api.anthropic.com",
249
- reasoning: true,
300
+ reasoning: false,
250
301
  input: ["text", "image"],
251
302
  cost: {
252
303
  input: 3,
253
304
  output: 15,
254
305
  cacheRead: 0.3,
255
- cacheWrite: 3.75,
256
- },
257
- contextWindow: 200000,
258
- maxTokens: 64000,
259
- },
260
- "claude-3-5-haiku-latest": {
261
- id: "claude-3-5-haiku-latest",
262
- name: "Claude Haiku 3.5",
263
- api: "anthropic-messages",
264
- provider: "anthropic",
265
- baseUrl: "https://api.anthropic.com",
266
- reasoning: false,
267
- input: ["text", "image"],
268
- cost: {
269
- input: 0.8,
270
- output: 4,
271
- cacheRead: 0.08,
272
- cacheWrite: 1,
306
+ cacheWrite: 0.3,
273
307
  },
274
308
  contextWindow: 200000,
275
- maxTokens: 8192,
309
+ maxTokens: 4096,
276
310
  },
277
- "claude-haiku-4-5": {
278
- id: "claude-haiku-4-5",
311
+ "claude-haiku-4-5-20251001": {
312
+ id: "claude-haiku-4-5-20251001",
279
313
  name: "Claude Haiku 4.5",
280
314
  api: "anthropic-messages",
281
315
  provider: "anthropic",
@@ -291,40 +325,6 @@ export const MODELS = {
291
325
  contextWindow: 200000,
292
326
  maxTokens: 64000,
293
327
  },
294
- "claude-opus-4-1": {
295
- id: "claude-opus-4-1",
296
- name: "Claude Opus 4.1",
297
- api: "anthropic-messages",
298
- provider: "anthropic",
299
- baseUrl: "https://api.anthropic.com",
300
- reasoning: true,
301
- input: ["text", "image"],
302
- cost: {
303
- input: 15,
304
- output: 75,
305
- cacheRead: 1.5,
306
- cacheWrite: 18.75,
307
- },
308
- contextWindow: 200000,
309
- maxTokens: 32000,
310
- },
311
- "claude-opus-4-0": {
312
- id: "claude-opus-4-0",
313
- name: "Claude Opus 4",
314
- api: "anthropic-messages",
315
- provider: "anthropic",
316
- baseUrl: "https://api.anthropic.com",
317
- reasoning: true,
318
- input: ["text", "image"],
319
- cost: {
320
- input: 15,
321
- output: 75,
322
- cacheRead: 1.5,
323
- cacheWrite: 18.75,
324
- },
325
- contextWindow: 200000,
326
- maxTokens: 32000,
327
- },
328
328
  },
329
329
  google: {
330
330
  "gemini-2.5-flash-preview-05-20": {
@@ -1801,6 +1801,23 @@ export const MODELS = {
1801
1801
  },
1802
1802
  },
1803
1803
  openrouter: {
1804
+ "minimax/minimax-m2:free": {
1805
+ id: "minimax/minimax-m2:free",
1806
+ name: "MiniMax: MiniMax M2 (free)",
1807
+ api: "openai-completions",
1808
+ provider: "openrouter",
1809
+ baseUrl: "https://openrouter.ai/api/v1",
1810
+ reasoning: true,
1811
+ input: ["text"],
1812
+ cost: {
1813
+ input: 0,
1814
+ output: 0,
1815
+ cacheRead: 0,
1816
+ cacheWrite: 0,
1817
+ },
1818
+ contextWindow: 204800,
1819
+ maxTokens: 131072,
1820
+ },
1804
1821
  "openrouter/andromeda-alpha": {
1805
1822
  id: "openrouter/andromeda-alpha",
1806
1823
  name: "Andromeda Alpha",
@@ -1971,6 +1988,23 @@ export const MODELS = {
1971
1988
  contextWindow: 202752,
1972
1989
  maxTokens: 202752,
1973
1990
  },
1991
+ "z-ai/glm-4.6:exacto": {
1992
+ id: "z-ai/glm-4.6:exacto",
1993
+ name: "Z.AI: GLM 4.6 (exacto)",
1994
+ api: "openai-completions",
1995
+ provider: "openrouter",
1996
+ baseUrl: "https://openrouter.ai/api/v1",
1997
+ reasoning: true,
1998
+ input: ["text"],
1999
+ cost: {
2000
+ input: 0.6,
2001
+ output: 1.9,
2002
+ cacheRead: 0,
2003
+ cacheWrite: 0,
2004
+ },
2005
+ contextWindow: 202752,
2006
+ maxTokens: 4096,
2007
+ },
1974
2008
  "deepseek/deepseek-v3.2-exp": {
1975
2009
  id: "deepseek/deepseek-v3.2-exp",
1976
2010
  name: "DeepSeek: DeepSeek V3.2 Exp",
@@ -2011,7 +2045,7 @@ export const MODELS = {
2011
2045
  api: "openai-completions",
2012
2046
  provider: "openrouter",
2013
2047
  baseUrl: "https://openrouter.ai/api/v1",
2014
- reasoning: true,
2048
+ reasoning: false,
2015
2049
  input: ["text", "image"],
2016
2050
  cost: {
2017
2051
  input: 0.3,
@@ -2073,6 +2107,23 @@ export const MODELS = {
2073
2107
  contextWindow: 163840,
2074
2108
  maxTokens: 163840,
2075
2109
  },
2110
+ "deepseek/deepseek-v3.1-terminus:exacto": {
2111
+ id: "deepseek/deepseek-v3.1-terminus:exacto",
2112
+ name: "DeepSeek: DeepSeek V3.1 Terminus (exacto)",
2113
+ api: "openai-completions",
2114
+ provider: "openrouter",
2115
+ baseUrl: "https://openrouter.ai/api/v1",
2116
+ reasoning: true,
2117
+ input: ["text"],
2118
+ cost: {
2119
+ input: 0.27,
2120
+ output: 1,
2121
+ cacheRead: 0,
2122
+ cacheWrite: 0,
2123
+ },
2124
+ contextWindow: 131072,
2125
+ maxTokens: 65536,
2126
+ },
2076
2127
  "alibaba/tongyi-deepresearch-30b-a3b:free": {
2077
2128
  id: "alibaba/tongyi-deepresearch-30b-a3b:free",
2078
2129
  name: "Tongyi DeepResearch 30B A3B (free)",
@@ -2133,13 +2184,13 @@ export const MODELS = {
2133
2184
  reasoning: true,
2134
2185
  input: ["text"],
2135
2186
  cost: {
2136
- input: 0.14,
2187
+ input: 0.15,
2137
2188
  output: 1.2,
2138
2189
  cacheRead: 0,
2139
2190
  cacheWrite: 0,
2140
2191
  },
2141
2192
  contextWindow: 262144,
2142
- maxTokens: 4096,
2193
+ maxTokens: 262144,
2143
2194
  },
2144
2195
  "qwen/qwen3-next-80b-a3b-instruct": {
2145
2196
  id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -2260,6 +2311,23 @@ export const MODELS = {
2260
2311
  contextWindow: 262144,
2261
2312
  maxTokens: 262144,
2262
2313
  },
2314
+ "moonshotai/kimi-k2-0905:exacto": {
2315
+ id: "moonshotai/kimi-k2-0905:exacto",
2316
+ name: "MoonshotAI: Kimi K2 0905 (exacto)",
2317
+ api: "openai-completions",
2318
+ provider: "openrouter",
2319
+ baseUrl: "https://openrouter.ai/api/v1",
2320
+ reasoning: false,
2321
+ input: ["text"],
2322
+ cost: {
2323
+ input: 0.6,
2324
+ output: 2.5,
2325
+ cacheRead: 0,
2326
+ cacheWrite: 0,
2327
+ },
2328
+ contextWindow: 262144,
2329
+ maxTokens: 4096,
2330
+ },
2263
2331
  "deepcogito/cogito-v2-preview-llama-70b": {
2264
2332
  id: "deepcogito/cogito-v2-preview-llama-70b",
2265
2333
  name: "Deep Cogito: Cogito V2 Preview Llama 70B",
@@ -2542,7 +2610,7 @@ export const MODELS = {
2542
2610
  input: ["text"],
2543
2611
  cost: {
2544
2612
  input: 0.35,
2545
- output: 1.5,
2613
+ output: 1.55,
2546
2614
  cacheRead: 0,
2547
2615
  cacheWrite: 0,
2548
2616
  },
@@ -2651,6 +2719,23 @@ export const MODELS = {
2651
2719
  contextWindow: 262144,
2652
2720
  maxTokens: 262144,
2653
2721
  },
2722
+ "qwen/qwen3-coder:exacto": {
2723
+ id: "qwen/qwen3-coder:exacto",
2724
+ name: "Qwen: Qwen3 Coder 480B A35B (exacto)",
2725
+ api: "openai-completions",
2726
+ provider: "openrouter",
2727
+ baseUrl: "https://openrouter.ai/api/v1",
2728
+ reasoning: true,
2729
+ input: ["text"],
2730
+ cost: {
2731
+ input: 0.38,
2732
+ output: 1.53,
2733
+ cacheRead: 0,
2734
+ cacheWrite: 0,
2735
+ },
2736
+ contextWindow: 262144,
2737
+ maxTokens: 262144,
2738
+ },
2654
2739
  "qwen/qwen3-235b-a22b-2507": {
2655
2740
  id: "qwen/qwen3-235b-a22b-2507",
2656
2741
  name: "Qwen: Qwen3 235B A22B Instruct 2507",
@@ -2821,9 +2906,9 @@ export const MODELS = {
2821
2906
  contextWindow: 40000,
2822
2907
  maxTokens: 40000,
2823
2908
  },
2824
- "mistralai/magistral-medium-2506": {
2825
- id: "mistralai/magistral-medium-2506",
2826
- name: "Mistral: Magistral Medium 2506",
2909
+ "mistralai/magistral-medium-2506:thinking": {
2910
+ id: "mistralai/magistral-medium-2506:thinking",
2911
+ name: "Mistral: Magistral Medium 2506 (thinking)",
2827
2912
  api: "openai-completions",
2828
2913
  provider: "openrouter",
2829
2914
  baseUrl: "https://openrouter.ai/api/v1",
@@ -2838,9 +2923,9 @@ export const MODELS = {
2838
2923
  contextWindow: 40960,
2839
2924
  maxTokens: 40000,
2840
2925
  },
2841
- "mistralai/magistral-medium-2506:thinking": {
2842
- id: "mistralai/magistral-medium-2506:thinking",
2843
- name: "Mistral: Magistral Medium 2506 (thinking)",
2926
+ "mistralai/magistral-medium-2506": {
2927
+ id: "mistralai/magistral-medium-2506",
2928
+ name: "Mistral: Magistral Medium 2506",
2844
2929
  api: "openai-completions",
2845
2930
  provider: "openrouter",
2846
2931
  baseUrl: "https://openrouter.ai/api/v1",
@@ -3025,6 +3110,23 @@ export const MODELS = {
3025
3110
  contextWindow: 40960,
3026
3111
  maxTokens: 40960,
3027
3112
  },
3113
+ "qwen/qwen3-8b": {
3114
+ id: "qwen/qwen3-8b",
3115
+ name: "Qwen: Qwen3 8B",
3116
+ api: "openai-completions",
3117
+ provider: "openrouter",
3118
+ baseUrl: "https://openrouter.ai/api/v1",
3119
+ reasoning: true,
3120
+ input: ["text"],
3121
+ cost: {
3122
+ input: 0.035,
3123
+ output: 0.13799999999999998,
3124
+ cacheRead: 0,
3125
+ cacheWrite: 0,
3126
+ },
3127
+ contextWindow: 128000,
3128
+ maxTokens: 20000,
3129
+ },
3028
3130
  "qwen/qwen3-14b": {
3029
3131
  id: "qwen/qwen3-14b",
3030
3132
  name: "Qwen: Qwen3 14B",
@@ -3209,8 +3311,8 @@ export const MODELS = {
3209
3311
  cacheRead: 0,
3210
3312
  cacheWrite: 0,
3211
3313
  },
3212
- contextWindow: 128000,
3213
- maxTokens: 4096,
3314
+ contextWindow: 96000,
3315
+ maxTokens: 96000,
3214
3316
  },
3215
3317
  "mistralai/mistral-small-3.1-24b-instruct": {
3216
3318
  id: "mistralai/mistral-small-3.1-24b-instruct",
@@ -3600,7 +3702,7 @@ export const MODELS = {
3600
3702
  cacheRead: 0,
3601
3703
  cacheWrite: 0,
3602
3704
  },
3603
- contextWindow: 128000,
3705
+ contextWindow: 131072,
3604
3706
  maxTokens: 4096,
3605
3707
  },
3606
3708
  "qwen/qwen-2.5-7b-instruct": {
@@ -3618,7 +3720,7 @@ export const MODELS = {
3618
3720
  cacheWrite: 0,
3619
3721
  },
3620
3722
  contextWindow: 32768,
3621
- maxTokens: 16384,
3723
+ maxTokens: 4096,
3622
3724
  },
3623
3725
  "nvidia/llama-3.1-nemotron-70b-instruct": {
3624
3726
  id: "nvidia/llama-3.1-nemotron-70b-instruct",
@@ -3705,34 +3807,34 @@ export const MODELS = {
3705
3807
  contextWindow: 32768,
3706
3808
  maxTokens: 4096,
3707
3809
  },
3708
- "cohere/command-r-plus-08-2024": {
3709
- id: "cohere/command-r-plus-08-2024",
3710
- name: "Cohere: Command R+ (08-2024)",
3810
+ "cohere/command-r-08-2024": {
3811
+ id: "cohere/command-r-08-2024",
3812
+ name: "Cohere: Command R (08-2024)",
3711
3813
  api: "openai-completions",
3712
3814
  provider: "openrouter",
3713
3815
  baseUrl: "https://openrouter.ai/api/v1",
3714
3816
  reasoning: false,
3715
3817
  input: ["text"],
3716
3818
  cost: {
3717
- input: 2.5,
3718
- output: 10,
3819
+ input: 0.15,
3820
+ output: 0.6,
3719
3821
  cacheRead: 0,
3720
3822
  cacheWrite: 0,
3721
3823
  },
3722
3824
  contextWindow: 128000,
3723
3825
  maxTokens: 4000,
3724
3826
  },
3725
- "cohere/command-r-08-2024": {
3726
- id: "cohere/command-r-08-2024",
3727
- name: "Cohere: Command R (08-2024)",
3827
+ "cohere/command-r-plus-08-2024": {
3828
+ id: "cohere/command-r-plus-08-2024",
3829
+ name: "Cohere: Command R+ (08-2024)",
3728
3830
  api: "openai-completions",
3729
3831
  provider: "openrouter",
3730
3832
  baseUrl: "https://openrouter.ai/api/v1",
3731
3833
  reasoning: false,
3732
3834
  input: ["text"],
3733
3835
  cost: {
3734
- input: 0.15,
3735
- output: 0.6,
3836
+ input: 2.5,
3837
+ output: 10,
3736
3838
  cacheRead: 0,
3737
3839
  cacheWrite: 0,
3738
3840
  },
@@ -3807,39 +3909,39 @@ export const MODELS = {
3807
3909
  contextWindow: 16384,
3808
3910
  maxTokens: 16384,
3809
3911
  },
3810
- "meta-llama/llama-3.1-405b-instruct": {
3811
- id: "meta-llama/llama-3.1-405b-instruct",
3812
- name: "Meta: Llama 3.1 405B Instruct",
3912
+ "meta-llama/llama-3.1-70b-instruct": {
3913
+ id: "meta-llama/llama-3.1-70b-instruct",
3914
+ name: "Meta: Llama 3.1 70B Instruct",
3813
3915
  api: "openai-completions",
3814
3916
  provider: "openrouter",
3815
3917
  baseUrl: "https://openrouter.ai/api/v1",
3816
3918
  reasoning: false,
3817
3919
  input: ["text"],
3818
3920
  cost: {
3819
- input: 0.7999999999999999,
3820
- output: 0.7999999999999999,
3921
+ input: 0.39999999999999997,
3922
+ output: 0.39999999999999997,
3821
3923
  cacheRead: 0,
3822
3924
  cacheWrite: 0,
3823
3925
  },
3824
- contextWindow: 32768,
3825
- maxTokens: 16384,
3926
+ contextWindow: 131072,
3927
+ maxTokens: 4096,
3826
3928
  },
3827
- "meta-llama/llama-3.1-70b-instruct": {
3828
- id: "meta-llama/llama-3.1-70b-instruct",
3829
- name: "Meta: Llama 3.1 70B Instruct",
3929
+ "meta-llama/llama-3.1-405b-instruct": {
3930
+ id: "meta-llama/llama-3.1-405b-instruct",
3931
+ name: "Meta: Llama 3.1 405B Instruct",
3830
3932
  api: "openai-completions",
3831
3933
  provider: "openrouter",
3832
3934
  baseUrl: "https://openrouter.ai/api/v1",
3833
3935
  reasoning: false,
3834
3936
  input: ["text"],
3835
3937
  cost: {
3836
- input: 0.39999999999999997,
3837
- output: 0.39999999999999997,
3938
+ input: 0.7999999999999999,
3939
+ output: 0.7999999999999999,
3838
3940
  cacheRead: 0,
3839
3941
  cacheWrite: 0,
3840
3942
  },
3841
- contextWindow: 131072,
3842
- maxTokens: 4096,
3943
+ contextWindow: 32768,
3944
+ maxTokens: 16384,
3843
3945
  },
3844
3946
  "mistralai/mistral-nemo": {
3845
3947
  id: "mistralai/mistral-nemo",
@@ -3960,34 +4062,34 @@ export const MODELS = {
3960
4062
  contextWindow: 128000,
3961
4063
  maxTokens: 4096,
3962
4064
  },
3963
- "meta-llama/llama-3-8b-instruct": {
3964
- id: "meta-llama/llama-3-8b-instruct",
3965
- name: "Meta: Llama 3 8B Instruct",
4065
+ "meta-llama/llama-3-70b-instruct": {
4066
+ id: "meta-llama/llama-3-70b-instruct",
4067
+ name: "Meta: Llama 3 70B Instruct",
3966
4068
  api: "openai-completions",
3967
4069
  provider: "openrouter",
3968
4070
  baseUrl: "https://openrouter.ai/api/v1",
3969
4071
  reasoning: false,
3970
4072
  input: ["text"],
3971
4073
  cost: {
3972
- input: 0.03,
3973
- output: 0.06,
4074
+ input: 0.3,
4075
+ output: 0.39999999999999997,
3974
4076
  cacheRead: 0,
3975
4077
  cacheWrite: 0,
3976
4078
  },
3977
4079
  contextWindow: 8192,
3978
4080
  maxTokens: 16384,
3979
4081
  },
3980
- "meta-llama/llama-3-70b-instruct": {
3981
- id: "meta-llama/llama-3-70b-instruct",
3982
- name: "Meta: Llama 3 70B Instruct",
4082
+ "meta-llama/llama-3-8b-instruct": {
4083
+ id: "meta-llama/llama-3-8b-instruct",
4084
+ name: "Meta: Llama 3 8B Instruct",
3983
4085
  api: "openai-completions",
3984
4086
  provider: "openrouter",
3985
4087
  baseUrl: "https://openrouter.ai/api/v1",
3986
4088
  reasoning: false,
3987
4089
  input: ["text"],
3988
4090
  cost: {
3989
- input: 0.3,
3990
- output: 0.39999999999999997,
4091
+ input: 0.03,
4092
+ output: 0.06,
3991
4093
  cacheRead: 0,
3992
4094
  cacheWrite: 0,
3993
4095
  },
@@ -4028,34 +4130,34 @@ export const MODELS = {
4028
4130
  contextWindow: 128000,
4029
4131
  maxTokens: 4096,
4030
4132
  },
4031
- "mistralai/mistral-small": {
4032
- id: "mistralai/mistral-small",
4033
- name: "Mistral Small",
4133
+ "mistralai/mistral-tiny": {
4134
+ id: "mistralai/mistral-tiny",
4135
+ name: "Mistral Tiny",
4034
4136
  api: "openai-completions",
4035
4137
  provider: "openrouter",
4036
4138
  baseUrl: "https://openrouter.ai/api/v1",
4037
4139
  reasoning: false,
4038
4140
  input: ["text"],
4039
4141
  cost: {
4040
- input: 0.19999999999999998,
4041
- output: 0.6,
4142
+ input: 0.25,
4143
+ output: 0.25,
4042
4144
  cacheRead: 0,
4043
4145
  cacheWrite: 0,
4044
4146
  },
4045
4147
  contextWindow: 32768,
4046
4148
  maxTokens: 4096,
4047
4149
  },
4048
- "mistralai/mistral-tiny": {
4049
- id: "mistralai/mistral-tiny",
4050
- name: "Mistral Tiny",
4150
+ "mistralai/mistral-small": {
4151
+ id: "mistralai/mistral-small",
4152
+ name: "Mistral Small",
4051
4153
  api: "openai-completions",
4052
4154
  provider: "openrouter",
4053
4155
  baseUrl: "https://openrouter.ai/api/v1",
4054
4156
  reasoning: false,
4055
4157
  input: ["text"],
4056
4158
  cost: {
4057
- input: 0.25,
4058
- output: 0.25,
4159
+ input: 0.19999999999999998,
4160
+ output: 0.6,
4059
4161
  cacheRead: 0,
4060
4162
  cacheWrite: 0,
4061
4163
  },